ReLayout: Versatile and Structure-Preserving Design Layout Editing via Relation-Aware Design Reconstruction

2026-02-01

AI Summary

This work addresses the challenge of automatically editing design layouts according to user intent while preserving structural relationships among unedited elements, particularly in the absence of triplet-based training data. The authors propose ReLayout, a novel framework that, for the first time, incorporates a graph encoding positional and dimensional relationships among layout elements as structural constraints. It introduces a Relationship-Aware Design Reconstruction (RADR) strategy to enable self-supervised layout editing without requiring real edited samples. ReLayout unifies diverse editing operations within a single multimodal large language model, supporting natural language–driven layout modifications. Experimental results demonstrate that ReLayout significantly outperforms existing baselines in terms of editing quality, accuracy, and structural consistency, with its effectiveness validated through both quantitative evaluation and user studies.

Technology Category

• Machine Learning: Large Multimodal Models (LMMs)
• Planning, Routing, and Scheduling: Replanning and Plan Repair
• Computer Vision: Diffusion Models for Vision

Application Category

• Graph Algorithms and Modeling for the Web: Foundation models and LLMs for Web-related graphs
• Search and Retrieval-Augmented AI: Web learning to rank, online learning, and counterfactual learning for ranking
• Responsible Web: Human-perceived consequences of algorithmic deployment on the web

Abstract

Automated redesign without manual adjustments marks a key step forward in the design workflow. In this work, we focus on a foundational redesign task termed design layout editing, which seeks to autonomously modify the geometric composition of a design based on user intents. To overcome the ambiguity of user needs expressed in natural language, we introduce four basic and important editing actions and standardize the format of editing operations. The underexplored task presents a unique challenge: satisfying specified editing operations while simultaneously preserving the layout structure of unedited elements. Besides, the scarcity of triplet (original design, editing operation, edited design) samples poses another formidable challenge. To this end, we present ReLayout, a novel framework for versatile and structure-preserving design layout editing that operates without triplet data. Specifically, ReLayout first introduces the relation graph, which contains the position and size relationships among unedited elements, as the constraint for layout structure preservation. Then, relation-aware design reconstruction (RADR) is proposed to bypass the data challenge. By learning to reconstruct a design from its elements, a relation graph, and a synthesized editing operation, RADR effectively emulates the editing process in a self-supervised manner. A multi-modal large language model serves as the backbone for RADR, unifying multiple editing actions within a single model and thus achieving versatile editing after fine-tuning. Qualitative, quantitative results and user studies show that ReLayout significantly outperforms the baseline models in terms of editing quality, accuracy, and layout structure preservation.

Problem

• design layout editing
• structure preservation
• relation-aware reconstruction
• triplet data scarcity
• automated redesign

Innovation

• relation graph
• structure-preserving
• self-supervised reconstruction
• design layout editing
• multi-modal LLM